HoloHema: Digital Holographic Hematology Analyzer

Andreas Gejl Madsen

doi:10.21996/0987122a-4cc6-48ce-bfc4-86e2e6d52f19

HoloHema: Digital Holographic Hematology Analyzer

Bidragets oversatte titel: HoloHema: Digital Holografisk Hæmatologi Analyzer

Andreas Gejl Madsen

Publikation: Afhandling › Ph.d.-afhandling

38 Downloads (Pure)

Abstract

Dette industrielle Ph.D.-projekt, udført i samarbejde mellem Radiometer Medical ApS og SDU Centre for Photonics Engineering ved Syddansk Universitet, undersøgte brugen af digital holografisk mikroskopi (DHM) til differentialtælling af hvide blodlegemer (dWBC) i point-of-care (PoC) apparater til akut pleje.

Der blev udviklet to DHM-prototyper: et indledende linsebaseret system, der dannede grundlag for algoritmeudvikling og eksperimentel validering af metoden, og som opnåede 89, 6% klassificeringsnøjagtighed på en 3-delt differentialtælling, samt et efterfølgende linseløst system med forenklet design og øget synsfelt (FoV). Begge metoder gjorde brug af convolutional neural networks (CNNs) til celleklassifikation.

Med yderligere optimeringer opnåede det linsefrie system klassificeringsnøjagtigheder på henholdsvis 92, 65% og 89, 44% på den 3-delte og 5-delte differentialtælling. Med det linsefrie system blev udledningen af monocyte distribution width (MDW), en biomarkør for sepsis, også demonstreret.

Derudover blev superopløsning og multi-bølgelængde DHM undersøgt for at forbedre den opnåede celleinformation. Endelig blev et proof-of-principle for et physics-informed neural network (PINN) til holografisk rekonstruktion implementeret, hvilket demonstrerede potentialet for rekonstruktion ved hjælp af machine learning (ML) teknikker.

Opsummerende repræsenterer dette arbejde en indledende udforskning af digital holografisk mikroskopi til differentialtællinger af hvide blodlegemer i PoC-apparater og lægger grundlaget for fremtidig forskning.

Bidragets oversatte titel	HoloHema: Digital Holografisk Hæmatologi Analyzer
Originalsprog	Engelsk
Bevilgende institution	Syddansk Universitet
Vejledere/rådgivere	Glückstad, Jesper, Vejleder Nielsen, Frank, Vejleder, Ekstern person Larsen, Peter emil, Vejleder, Ekstern person Panah, Mohammad Aryaee, Vejleder, Ekstern person
Eksterne samarbejdspartnere	Radiometer Medical ApS
Dato for forsvar	5. mar. 2025
Udgiver	Syddansk Universitet. Det Tekniske Fakultet
DOI	https://doi.org/10.21996/0987122a-4cc6-48ce-bfc4-86e2e6d52f19
Status	Udgivet - 11. mar. 2025

Dokumenter og links

10.21996/0987122a-4cc6-48ce-bfc4-86e2e6d52f19

Open Access VersionForlagets udgivne version, 204 MB

SDU link

Tjek adgangen til materialet i Syddansk Universitetsbiblioteks søgemaskine

7 Tidsskriftartikel

Axial HoloTile: Extended Depth-of-Focus of Dynamic Holographic Light Projections
Madsen, A. G. & Glückstad, J., mar. 2025, I: Optics Communications. 577, 6 s., 131441.
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning

Åben adgang
Fil
28 Downloads (Pure)
Gabor-type holography solved analytically for complex-valued phase disks
Glückstad, J. & Madsen, A. G., 15. maj 2024, I: Optics Communications. 559, 7 s., 130400.
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review

Åben adgang
Fil
22 Downloads (Pure)
HoloTile light engine: new digital holographic modalities and applications (Invited paper)
Glückstad, J. & Madsen, A. G., mar. 2024, I: Reports on Progress in Physics. 87, 3, 14 s., 034401.
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review

Fil
16 Downloads (Pure)

Citationsformater

@misc{0987122a4cc648cebfc486e2e6d52f19,

title = "HoloHema: Digital Holographic Hematology Analyzer",

abstract = "This industrial Ph.D. project, carried out in collaboration between Radiometer Medical ApS and SDU Centre for Photonics Engineering at the University of Southern Denmark, explored the use of digital holographic microscopy (DHM) for the purposes of differential white blood cell counts (dWBCs) in point-of-care (PoC) devices for acute care settings. Two DHM prototypes were developed; an initial lens-based system serving as the foundation for algorithm development, and experimental validation of the approach, achieving 89.6\% classification accuracy on a 3-part differential, and a subsequent lensless system for simplified design and increased field-ofview (FoV). Both prototypes employed convolutional neural networks (CNNs) for cell classification. With further optimizations, the lensless system achieved classification accuracies of 92.65\% and 89.44\% on the 3-part and 5-part differential, respectively. With the lensless system, the derivation of the monocyte distribution width (MDW), a biomarker for sepsis, was also demonstrated.Additionally, pixel super-resolution and multi-wavelength DHM approaches were investigated to enhance the obtained cell information. Finally, a proof-of-principle physics-informed neural network (PINN) for holographic reconstruction was implemented, demonstrating the potential for machine learning (ML) reconstruction techniques.In summary, this work represents an initial exploration of DHM for dWBC in PoC devices, laying the groundwork for future research.",

author = "Madsen, \{Andreas Gejl\}",

year = "2025",

month = mar,

day = "11",

doi = "10.21996/0987122a-4cc6-48ce-bfc4-86e2e6d52f19",

language = "English",

publisher = "Syddansk Universitet. Det Tekniske Fakultet",

address = "Denmark",

school = "SDU",

}

TY - GEN

T1 - HoloHema

T2 - Digital Holographic Hematology Analyzer

AU - Madsen, Andreas Gejl

PY - 2025/3/11

Y1 - 2025/3/11

N2 - This industrial Ph.D. project, carried out in collaboration between Radiometer Medical ApS and SDU Centre for Photonics Engineering at the University of Southern Denmark, explored the use of digital holographic microscopy (DHM) for the purposes of differential white blood cell counts (dWBCs) in point-of-care (PoC) devices for acute care settings. Two DHM prototypes were developed; an initial lens-based system serving as the foundation for algorithm development, and experimental validation of the approach, achieving 89.6% classification accuracy on a 3-part differential, and a subsequent lensless system for simplified design and increased field-ofview (FoV). Both prototypes employed convolutional neural networks (CNNs) for cell classification. With further optimizations, the lensless system achieved classification accuracies of 92.65% and 89.44% on the 3-part and 5-part differential, respectively. With the lensless system, the derivation of the monocyte distribution width (MDW), a biomarker for sepsis, was also demonstrated.Additionally, pixel super-resolution and multi-wavelength DHM approaches were investigated to enhance the obtained cell information. Finally, a proof-of-principle physics-informed neural network (PINN) for holographic reconstruction was implemented, demonstrating the potential for machine learning (ML) reconstruction techniques.In summary, this work represents an initial exploration of DHM for dWBC in PoC devices, laying the groundwork for future research.

AB - This industrial Ph.D. project, carried out in collaboration between Radiometer Medical ApS and SDU Centre for Photonics Engineering at the University of Southern Denmark, explored the use of digital holographic microscopy (DHM) for the purposes of differential white blood cell counts (dWBCs) in point-of-care (PoC) devices for acute care settings. Two DHM prototypes were developed; an initial lens-based system serving as the foundation for algorithm development, and experimental validation of the approach, achieving 89.6% classification accuracy on a 3-part differential, and a subsequent lensless system for simplified design and increased field-ofview (FoV). Both prototypes employed convolutional neural networks (CNNs) for cell classification. With further optimizations, the lensless system achieved classification accuracies of 92.65% and 89.44% on the 3-part and 5-part differential, respectively. With the lensless system, the derivation of the monocyte distribution width (MDW), a biomarker for sepsis, was also demonstrated.Additionally, pixel super-resolution and multi-wavelength DHM approaches were investigated to enhance the obtained cell information. Finally, a proof-of-principle physics-informed neural network (PINN) for holographic reconstruction was implemented, demonstrating the potential for machine learning (ML) reconstruction techniques.In summary, this work represents an initial exploration of DHM for dWBC in PoC devices, laying the groundwork for future research.

U2 - 10.21996/0987122a-4cc6-48ce-bfc4-86e2e6d52f19

DO - 10.21996/0987122a-4cc6-48ce-bfc4-86e2e6d52f19

M3 - Ph.D. thesis

PB - Syddansk Universitet. Det Tekniske Fakultet

ER -

HoloHema: Digital Holographic Hematology Analyzer

Abstract

Dokumenter og links

SDU link

Fingeraftryk

Relaterede publikationer

Axial HoloTile: Extended Depth-of-Focus of Dynamic Holographic Light Projections

Gabor-type holography solved analytically for complex-valued phase disks

HoloTile light engine: new digital holographic modalities and applications (Invited paper)

Citationsformater